检索结果-内蒙古大学图书馆

30th International Joint Conference on Artificial Intelligence, IJCAI 2021

作者： Jiang, Haobo Qian, Jianjun Xie, Jin Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9780999241196

Point cloud registration is a fundamental problem in 3D computer vision. In this paper, we cast point cloud registration into a planning problem in reinforcement learning, which can seek the transformation between the source and target point clouds through trial and error. By modeling the point cloud registration process as a Markov decision process (MDP), we develop a latent dynamic model of point clouds, consisting of a transformation network and evaluation network. The transformation network aims to predict the new transformed feature of the point cloud after performing a rigid transformation (i.e., action) on it while the evaluation network aims to predict the alignment precision between the transformed source point cloud and target point cloud as the reward signal. Once the dynamic model of the point cloud is trained, we employ the cross-entropy method (CEM) to iteratively update the planning policy by maximizing the rewards in the point cloud registration process. Thus, the optimal policy, i.e., the transformation between the source and target point clouds, can be obtained via gradually narrowing the search space of the transformation. Experimental results on ModelNet40 and 7Scene benchmark datasets demonstrate that our method can yield good registration performance in an unsupervised manner. © 2021 International Joint Conferences on Artificial Intelligence. All rights reserved.

关键词： Dynamic models

来源：评论

学校读者我要写书评

暂无评论

Maneuvering target tracking based on fuzzy reasoning

引用

Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics 2009年第3期31卷 541-544页

作者： Han, Hong Chen, Zhao-Ping Jiao, Li-Cheng Zhi, Jian-Wei Key Lab. of Intelligent Perception and Image Understanding Inst. of Intelligent Information Processing Xidian Univ. Xi'an 710071 China

The performance of the 'current' statistical model algorithm gets worse when there is a sudden maneuver. To solve this problem, an improved algorithm is presented. This algorithm is implemented through a pair of parallel adaptive filters together with information fusion technique. By introducing the state information of targets, the output of the fuzzy system can adjust the predicted covariance of the filter adaptively. The simulation results show that the proposed algorithm has better performance when there is a sudden maneuver.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Unified Density-Aware image Dehazing and Object Detection in Real-World Hazy Scenes 15th

Unified Density-Aware Image Dehazing and Object Detection in...

引用

15th Asian Conference on Computer Vision, ACCV 2020

作者： Zhang, Zhengxi Zhao, Liang Liu, Yunan Zhang, Shanshan Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High -Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9783030695378

It is an important yet challenging task to detect objects on hazy images in real-world applications. The major challenge comes from low visual quality and large haze density variations. In this work, we aim to jointly solve the image dehazing and the object detection tasks in real hazy scenarios by using haze density as prior knowledge. Our proposed Unified Dehazing and Detection (UDnD) framework consists of three parts: a residual-aware haze density classifier, a density-aware dehazing network, and a density-aware object detector. First, the classifier exploits the residuals of hazy images to accurately predict density levels, which provide rich domain knowledge for the subsequent two tasks. Then, we design respectively a High-Resolution Dehazing Network (HRDN) and a Faster R-CNN-based multi-domain object detector to leverage the extracted density information and tackle hazy object detection. Experiments demonstrate that UDnD performs favorably against other methods for object detection in real-world hazy scenes. Also, HRDN achieves better results than state-of-the-art dehazing methods in terms of PSNR and SSIM. Hence, HRDN can conduct haze removal effectively, based on which UDnD is able to provide high-quality detection results. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Global Spatio-Temporal Fusion-based Traffic Prediction Algorithm with Anomaly Aware

Global Spatio-Temporal Fusion-based Traffic Prediction Algor...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Liu, Chaoqun Li, Xuanpeng Gong, Chen Li, Guangyu Nanjing University of Science and Technology Pca Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security China Southeast University Nanjing210094 China

ISBN: (纸本)9798350351255

Traffic prediction is an indispensable component of urban planning and traffic management. Achieving accurate traffic prediction hinges on the ability to capture the potential spatio-temporal relationships among road sensors. However, the majority of existing works focus on local short-term spatiotemporal correlations, failing to fully consider the interactions of different sensors in the long-term state. In addition, these works do not analyze the influences of anomalous factors, or have insufficient ability to extract personalized features of anomalous factors, which make them ineffectively capture their spatiotemporal influences on traffic prediction. To address the aforementioned issues, We propose a global spatio-temporal fusionbased traffic prediction algorithm that incorporates anomaly awareness. Initially, based on the designed anomaly detection network, we construct an efficient anomalous factors impacting module (AFIM), to evaluate the spatio-temporal impact of unexpected external events on traffic prediction. Furthermore, we propose a multi-scale spatio-temporal feature fusion module (MTSFFL) based on the transformer architecture, to obtain all possible both long and short term correlations among different sensors in a wide-area traffic environment for accurate prediction of traffic flow. Finally, experiments are implemented based on real-scenario public transportation datasets (PEMS04 and PEMS08) to demonstrate that our approach can achieve stateof-the-art performance. © 2024 IEEE.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Immune clonal multi-objective algorithm for unsupervised feature selection

引用

Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University 2010年第1期37卷 18-22页

作者： Shang, Rong-Hua Jiao, Li-Cheng Wu, Jian-She Ma, Wen-Ping Li, Yang-Yang Ministry of Education Key Lab. of Intelligent Perception and Image Understanding Xidian Univ. Xi'an 710071 China

The unsupervised feature selection is transferred into a multiobjective optimization problem, and the immune clonal selection algorithm for multi-objective optimization is applied to solve it. Firstly, the unsupervised feature selection problem is translated into multi-objective problem. Secondly, the model and the objective functions are constructed. Lastly, each feature of significance is optimized by increasing the significance of the related features and decreasing the significance of the unrelated features. Experimental results on UCI data sets show that the error recognition rate is decreased and that the effectiveness and potential of the method are validated.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

image processing enhancing dictionary-based super-resolution using nonlocal total variation regularization

引用

Optical Engineering 2013年第1期52卷

作者： Jung, Cheolkon Ju, Junwei Jiao, Licheng Yang, Yanru Key Lab of Intelligent Perception Image Understanding of Ministry of Education of China Xi'an 710071 China

The dictionary-based super-resolution (SR) method has received much attention in recent years because sparse representation is very effective for image restoration tasks. By sparse representation, original image patches are represented as a sparse linear combination of atoms in an over-complete dictionary. However, the dictionary-based SR approach has some disadvantages in that it produces annoying ringing artifacts, especially along the object boundaries and is not effective in reconstructing images that contain patterns with strong edges. We enhance the dictionary-based SR using nonlocal total variation regularization. In the training stage, we jointly train two dictionaries, Dh and D1, from the low-resolution (LR) and high-resolution (HR) training image patches by using the K-singular value decomposition (KSVD) algorithm as in conventional methods. In the synthesis stage, we obtain the sparse coefficient vector from the LR test image over the LR dictionary, and reconstruct SR patches using the coefficient vector over the HR dictionary. Then, we employ nonlocal total variation regularization to remove annoying ringing artifacts and recover the patterns with strong edges in images. Experimental results on various test images demonstrate that the proposed method is very effective in enhancing the dictionary-based SR approaches in terms of quantitative performance and visual quality. © 2013 Society of Photo-Optical Instrumentation Engineers (SPIE).

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Change detection in multitemporal remote sensing images based on local mean dynamic Fisher discriminant analysis

引用

Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University 2012年第5期39卷 12-17+29页

作者： Xin, Fangfang Jiao, Licheng Wang, Lingxia Wang, Guiting Ministry of Education Key Lab. of Intelligent Perception and Image Understanding Xidian Univ. Xi'an 710071 China

This paper proposes a novel change detection technique, which treats the detection problem as a classifier problem and uses the improved dynamic Fisher classifier to identify the changes in the joint intensity histogram. By considering the relationship between the pixel and its neighborhood, local mean dynamic Fisher discriminant analysis (LMDFDA) is proposed to introduce the neighborhood's information. Meanwhile, the parameters of the classifier are adjusted according to the current detection result, which avoids the influences of initial conditions. The proposed method is distribution free, context-sensitive and not affected by comparison operators. Experiments show that the proposed algorithm is effective and feasible for real multi-temporal remote sensing images.

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Assignment problem based deep embedding 1

引用

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Zheng, Ruishen Xie, Jin Qian, Jianjun Yang, Jian PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

How to measure the similarity of samples is a fundamental problem in many computer vision tasks such as retrieval and clustering. Due to the rapid development of deep neural networks, deep metric learning has been widely studied. Some studies focus on the hard sample mining strategy for triplet loss. We observe that hard mining strategies are also vital for contrastive loss. But the hardest mining strategy for contrastive loss is sensitive to outliers. In this paper, based on combinatorial information of sample pairs, we propose a novel linear assignment problem based hard sample mining strategy for contrastive loss to learn feature embeddings. Specifically, our method can assign 0/1 weight to sample pairs for the hard sample selection by maximizing a linear assignment loss and ensure that each sample is only included by one pair for the optimization. Our method can obtain the state-of-the-art performance on the CUB-200-2011, Cars196, and In-shop datasets with the GoogLeNet network. © Springer Nature Switzerland AG 2019.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Collaborative filtering algorithm via compressing the sparse user-rating-data matrix

引用

Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University 2009年第4期36卷 614-618+638页

作者： Hou, Cui-Qin Jiao, Li-Cheng Zhang, Wen-Ge Ministry of Education Key Lab. of Intelligent Perception and Image Understanding Research Inst. of Intelligent Information Processing Xidian Univ. Xi'an 710071 China

The paper proposes a novel memory-based collaborative filtering algorithm-Multi-label Probabilistic Latent Semantic Analysis based Collaborative Filtering, which improves the quality of recommendations by reducing the dimension of the user-rating-data matrix by multi-label probabilistic latent semantic analysis when the matrix is extremely sparse. Firstly, it confines the set of latent variables of probability latent semantic analysis to the set of multi-label of items to make latent variables have meanings of corresponding labels. Then it learns the probabilistic distribution of latent variables, i.e., the model of use's interest, to compress the user-rating-data matrix. Finally, it computes the similarity between different users based on the above learned model and makes recommendations. Compared to memory-based collaborative filtering algorithms, the proposed algorithm decreases the mean absolute error 4 percents averagely on test dataset by reducing the dimension of the user-rating-data matrix. The proposed algorithm makes the recommendation system understandable and obtains competitive recommendations compared to the filtering algorithm which reduces the dimension of the user-rating-data matrix by probabilistic latent semantic analysis.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

An improved spectral clustering ensemble algorithm for POLSAR land cover classification

引用

International Journal of Earth Sciences and Engineering 2015年第2期8卷 937-943页

作者： Liu, Lu Shi, Junfei Jiao, Licheng Jin, Shaohui Key Lab. of Intelligent Perception and Image Understanding of Ministry of Education Xidian Univ. Xi’an China

In this paper, a Laplacian eigenmap and dictionary learning based spectral clustering ensemble (LE-DLSCE) algorithm for polarimetric SAR (PolSAR) land cover classification is proposed to solve problems of high computational complexity and instability of spectral clustering (SC) *** polarimetric feature and spatial texture feature are combined to obtain the feature matrix of PolSAR image. Laplacian eigenmap (LE) which reduces the data amount processed by SC is then applied to compress the feature matrix. Dictionary learning based sample selection method is used to increase the information involved in sample points and avoid the instability classification results caused by random sampling of Nyström approximation. The Markov Random Field (MRF) potential function is employed to construct the similarity matrix by combined similarity measures. Finally, multiple individual PolSAR classification results are obtained and integrated by an ensemble strategy. The experimental results demonstrate that the proposed method improves the classification performance, having advantages in region homogeneity and edge preservationand achieving stable results. © 2015 CAFET-INNOVA TECHNICAL SOCIETY. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：